Model: GELU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1910 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.6759. Min Range: -5.6759

Max Act: 5.6759. Min Act: -0.1700

Data Index: 225331 (C4 (Web Text))

Max Activating Token Index: 266

Text #1

Max Range: 5.6759. Min Range: -5.6759

Max Act: 5.5822. Min Act: -0.1700

Data Index: 22235 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 5.6759. Min Range: -5.6759

Max Act: 5.6447. Min Act: -0.1700

Data Index: 719244 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 5.6759. Min Range: -5.6759

Max Act: 5.5197. Min Act: -0.1700

Data Index: 290222 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 5.6759. Min Range: -5.6759

Max Act: 5.5822. Min Act: -0.1700

Data Index: 735669 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 5.6759. Min Range: -5.6759

Max Act: 5.5822. Min Act: -0.1700

Data Index: 755104 (C4 (Web Text))

Max Activating Token Index: 359

Text #6

Max Range: 5.6759. Min Range: -5.6759

Max Act: 5.4572. Min Act: -0.1700

Data Index: 138620 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 5.6759. Min Range: -5.6759

Max Act: 5.4259. Min Act: -0.1700

Data Index: 854018 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 5.6759. Min Range: -5.6759

Max Act: 5.4884. Min Act: -0.1700

Data Index: 145309 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 5.6759. Min Range: -5.6759

Max Act: 5.4572. Min Act: -0.1700

Data Index: 246877 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 5.6759. Min Range: -5.6759

Max Act: 5.4259. Min Act: -0.1700

Data Index: 541041 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 5.6759. Min Range: -5.6759

Max Act: 5.4884. Min Act: -0.1700

Data Index: 830162 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 5.6759. Min Range: -5.6759

Max Act: 5.3634. Min Act: -0.1700

Data Index: 637447 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 5.6759. Min Range: -5.6759

Max Act: 5.4259. Min Act: -0.1700

Data Index: 200108 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 5.6759. Min Range: -5.6759

Max Act: 5.4259. Min Act: -0.1700

Data Index: 124908 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 5.6759. Min Range: -5.6759

Max Act: 5.3947. Min Act: -0.1700

Data Index: 622516 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 5.6759. Min Range: -5.6759

Max Act: 5.4884. Min Act: -0.1700

Data Index: 835025 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 5.6759. Min Range: -5.6759

Max Act: 5.3947. Min Act: -0.1700

Data Index: 656091 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 5.6759. Min Range: -5.6759

Max Act: 5.2072. Min Act: -0.1700

Data Index: 385167 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 5.6759. Min Range: -5.6759

Max Act: 5.3947. Min Act: -0.1700

Data Index: 821999 (C4 (Web Text))

Max Activating Token Index: 390